Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data
Paper
•
2601.15158
•
Published
Yuval Ran-Milo
YuvMil
·
AI & ML interests
None yet
Recent Activity
authored
a paper
1 day ago
Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data
Organizations
None yet
authored
a
paper
1 day ago